I met Australia's Assistant Minister for Defence last Friday. I asked him to write an email to the Minister in charge of AI, asking him to establish an AI Safety Institute. He said he would. He also seemed on board with not having fully autonomous AI weaponry.

All because I sent one email asking for a meeting + had said meeting. 

Advocacy might be the lowest hanging fruit in AI Safety.

A periodic reminder that you can just email politicians and then meet them (see screenshot below).

My previous take on writing to Politicians got numbers, so I figured I'd post the email I send below.

I am going to make some updates, but this is the latest version:

---

Hi [Politician]

My name is Yanni Kyriacos, I live in Coogee, just down the road from your electorate.

If you're up for it, I'd like to meet to discuss the risks posed by AI. In addition to my day job building startups, I do community / movement building in the AI Safety / AI existential risk space. You can learn more about AI Safety ANZ by joining our Facebook group here or the PauseAI movement here. I am also a signatory of Australians for AI Safety - a group that has called for the Australian government to set up an AI Commission (or similar body).

Recently I worked with Australian AI experts (such as Good Ancestors Policy) in making a submission to the recent safe and response AI consultation process. In the letter, we called on the government to acknowledge the potential catastrophic and existential risks from artificial intelligence. More on that can be found here.

There are many immediate risks from already existing AI systems like ChatGPT or Midjourney, such as disinformation or improper implementation in various businesses. In the not-so-distant future, certain safety nets will need to be activated (such as a Universal Basic Income policy) in the event of mass unemployment due to displacement of jobs with robots and AI systems.

But of greatest concern is the speed at which we are marching towards AGI (artificial general intelligence) – systems that will have cognitive abilities at or above human level.

Half of AI researchers believe that there is a 10% or greater chance that the invention of artificial superintelligence will mean the end of humanity. Among AI safety scientists, this chance is estimated to be an average of 30%. And these levels of risk aren’t just a concern for people in the far-distant future, with prediction markets such as Metaculus showing these kinds of AI could be invented in the next term of government.

Notable examples of individuals sounding the alarm are Prof. Geoffrey Hinton and Prof. Yoshua Bengio, both Turing-award winners and pioneers of the deep learning methods that are currently achieving the most success. The existential risk of AI has been acknowledged by hundreds of scientists, the UN, the US and recently the EU.

To make a long story short: we don't know how to align AI with the complex goals and values that humans have. When a superintelligent system is realised, there is a significant risk it will pursue a misaligned goal without us being able to stop it. And even if such a superhuman AI remains under human control, the person (or government) wielding such a power could use this to drastically, irreversibly change the world. Such an AI could be used to develop new technologies and weapons, manipulate masses of people or topple governments.

The advancements in the AI landscape have progressed much faster than anticipated. In 2020, it was estimated that an AI would pass university entrance exams by 2050. This goal was achieved in March 2023 by the system GPT-4 from OpenAI. These massive, unexpected leaps have prompted many experts to request a pause in AI development through an open letter to major AI companies. The letter has been signed over 33,000 times so far, including many AI researchers and tech figures.

Unfortunately, it seems that companies are not willing to jeopardise their competitive position by voluntarily halting development. A pause would need to be imposed by a government. Luckily, there seems to be broad support for slowing down AI development. A recent poll indicates that 63% of American support regulations to prevent AI companies from building superintelligent AI. At the national level, a pause is also challenging because countries have incentives to not fall behind in AI capabilities. That's why we need an international solution.

The UK organised an AI Safety Summit on November 1st and 2nd at Bletchley Park. We hoped that during this summit, leaders would work towards sensible solutions that prevent the very worst of the risks that AI poses. As such I was excited to see that Australia signed the The Bletchley Declaration, agreeing that this risk is real and warrants coordinated international action. However, the recent policy statements by Minister Husic don't seem to align with the urgency that experts are seeing. The last safe moment to act could be very soon.

The Summit has not yet produced an international agreement or policy. We have seen proposals being written by the US Senate, and even AI company CEOs have said there is “overwhelming consensus” that regulation is needed. But no proposal so far has seriously considered ways to slow down or prevent a superintelligent AI from being created. I am afraid that lobbying efforts by AI companies to keep regulation at a minimum are turning out to be highly effective.

It's essential that the government follows through on its commitment at Bletchley Park to create a national or regional AI safety body. We have such bodies for everything from the risk of plane crashes to the risk of tsunamis. We urgently need one on ensuring the safety of AI systems.

Anyway, I'd love to discuss this more in person or via zoom if you're in town soon.

Let me know what you think.
Cheers,,

Yanni 

RIP to any posts on anything earnest over the last 48 hours. Maybe in future we don't tag anything April Fools and it is otherwise a complete blackout on serious posts 😅

BrownHairedEevee @ 2024-04-02T05:24 (+6)

How about making the April Fool's Day tag visible on the forum frontpage, like so?

Darren McKee @ 2024-04-02T15:47 (+12)

Something(!) needs to be done. Otherwise, it's just a mess for clarity and the communication of ideas. 

Yanni Kyriacos @ 2024-04-02T20:04 (+8)

I think the hilarity is in the confusion / click bait. Your idea would rob us of this! I think the best course of action is for anyone with a serious post to wait until April 3 :|

tobytrem @ 2024-04-03T08:47 (+2)

Not a solution to everything mentioned here- but a reminder that you can click "customize feed" at the top of the page and remove all posts tagged april fools.

Yanni Kyriacos @ 2024-04-04T10:31 (+1)

nah let's lean all the way in, for one day a year, the wild west out here.

Yanni Kyriacos @ 2024-04-03T00:56 (+1)

Damn just had the idea of a "Who wants to be Fired?" post. 

I think if you work in AI Safety (or want to) it is very important to be extremely skeptical of your motivations for working in the space. This applies to being skepticism of interventions within AI Safety as well. 

For example, EAs (like most people!) are motivated to do things they're (1) good at (2) see as high status (i.e. people very quietly ask themselves 'would someone who I perceive as high status approve of my belief or action?'). Based on this, I am worried that (1) many EAs find protesting AI labs (and advocating for a Pause in general) cringy and/or awkward (2) Ignore the potential impact of organisations such as PauseAI. 

We might all literally die soon because of misaligned AI, so what I'm recommending is that anyone seriously considering AI Safety as a career path spends a lot of time on the question of 'what is really motivating me here?' 

I have written 7 emails to 7 Politicians aiming to meet them to discuss AI Safety, and already have 2 meetings.

Normally, I'd put this kind of post on twitter, but I'm not on twitter, so it is here instead.

I just want people to know that if they're worried about AI Safety, believe more government engagement is a good thing and can hold a decent conversation (i.e. you understand the issue and are a good verbal/written communicator), then this could be an underrated path to high impact.

Another thing that is great about it is you can choose how many emails to send and how many meetings to have. So it can be done on the side of a "day job".

[GIF] A feature I'd love on the forum: while posts are read back to you, the part of the text that is being read is highlighted. This exists on Naturalreaders.com and would love to see it here (great for people who have wandering minds like me)

I think acting on the margins is still very underrated. For e.g. I think 5x the amount of advocacy for a Pause on capabilities development of frontier AI models would be great. I also think in 12 months time it would be fine for me to reevaluate this take and say something like 'ok that's enough Pause advocacy'.

Basically, you shouldn't feel 'locked in' to any view. And if you're starting to feel like you're part of a tribe, then that could be a bad sign you've been psychographically locked in.

The general public wants frontier AI models regulated and there doesn't seem to be grassroots focussed orgs attempting to capture and funnel this energy into influencing politicians. E.g. via this kind of activity. This seems like massively low hanging fruit. An example of an organisation that does this (but for GH&W) is Results Australia. Someone should set up such an org.

So I did a quick check today - I've sent 19 emails to politicians about AI Safety / x-risk and received 4 meetings. They've all had a really good vibe, and I've managed to get each of them to commit to something small (e.g. email XYZ person about setting up an AI Safety Institute). I'm pretty happy with the hit rate (4/19). I might do another forum quick take once I've sent 50.

Be the meme you want to see in the world (screenshot).


 

What is your best guess of the overall impact of 80k interviewing AI labs on their podcast + listing AI lab vacant roles?

Poll: https://www.guidedtrack.com/programs/qj0ykwn/run

It breaks my heart when I see eulogy posts on the forum. And while I greatly appreciate people going to the effort of writing them (while presumably experiencing grief), it still doesn't feel like enough. We're talking about people that dedicated their lives to doing good, and all they get is a post. I don't have a suggestion to address this 'problem', and some may even feel that a post is enough, but I don't. Maybe there is no good answer and death just sucks. I dunno.

I think https://www.wakingup.com/ should be considered for effective organisation status. It donates 10% of revenue to the most effective causes and I think reaching nondual states of awakening could be one of the most effective ways for people in rich countries to improve their wellbeing. 

This is an extremely "EA" request from me but I feel like we need a word for people (i.e. me) who are Vegans but will eat animal products if they're about to be thrown out. OpportuVegan? UtilaVegan?

I think the average EA worries too much about negative PR related to EA. I think this is a shame because EA didn't get to where it is now because it concerned itself with PR. It got here through good-old-fashioned hard work (and good thinking ofc).

Two examples:

1. FTX. 

2. OpenAI board drama.

On the whole, I think there was way too much time spent thinking and talking about these massive outliers and it would have been better if 95%+ of EAs put their head down and did what they do best - get back to work.

I think it is good to discuss and take action on the issues at a concrete level, but not to talk about how this affects "what people think of EA". EA overindexing on conscientiousness can have negative consequences!

What is your "Pens Down" moment? 

"Pens Down" to mean 'Artificial Super Intelligence in my opinion is close enough that it no longer makes sense to work on whatever else I'm currently working on, because we're about to undergo radical amounts of change very soon/quickly'.

For me, it is probably when we have something as powerful as GPT-4 except it is agentic and costs less than $100 / month. So, that looks like a digital personal assistant that can execute an instruction like "have a TV delivered for me by X date, under Y price and organise installation and wall mounting."

This is obviously a question mainly for people who don't work full time on AI Safety.

A potential failure mode of 80k recommending EAs work at AI labs:

1. 80k promotes a safety related job within a leading AI lab.
2. 80k's audience (purposefully) skews to high prospect candidates (HPC) - smarter, richer, better connected vs average. 
3. HPC applies for and gets safety role within AI lab.
4. HPC candidate stays at the lab but moves roles. 
5. Now we have a smart, rich, well connected person no longer in safety but in capabilities.

I think this is sufficiently important / likely that 80k should consider tracking these people over time to see if this is a real issue.

Has anyone seen an analysis that takes seriously the idea that people should eat some fruits, vegetables and legumes over others based on how much animal suffering they each cause?

I.e. don't eat X fruit, eat Y one instead, because X fruit is [e.g.] harvested in Z way, which kills more [insert plausibly sentient creature].

Even though I've been in the AI Safety space for ~ 2 years, I can't shake the feeling that every living thing dying painlessly in its sleep overnight (due to AI killing us) isn't as bad as (i.e. is 'better' than) hundreds of millions of people living in poverty and/or hundreds of billions of animals being tortured. 

This makes me suspicious of my motivations. I think I do the work partly because I kinda feel the loss of future generations, but mainly because AI Safety still feels so neglected (and my counter factual impact here is larger).

I don't think s-risks play much of a role in this, although they have in the past (here, I define disempowerment due to AGI, or authoritarian use of AGI as s-risks).

Something I'm confused about: what is the threshold that needs meeting for the majority of people in the EA community to say something like "it would be better if EAs didn't work at OpenAI"?

Imagining the following hypothetical scenarios over 2024/25, I can't predict confidently whether they'd individually cause that response within EA?

1. Ten-fifteen more OpenAI staff quit for varied and unclear reasons. No public info is gained outside of rumours
2. There is another board shakeup because senior leaders seem worried about Altman. Altman stays on
3. Superalignment team is disbanded
4. OpenAI doesn't let UK or US AISI's safety test GPT5/6 before release
5. There are strong rumours they've achieved weakly general AGI internally at end of 2025

I think it would be good if lots of EAs answered this twitter poll, so we could get a better sense for the communities views on the topic of Enlightenment / Awakening: https://twitter.com/SpencrGreenberg/status/1782525718586413085?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Etweet

The catchphrase I walk around with in my head regarding the optimal strategy for AI Safety is something like: Creating Superintelligent Artificial Agents* (SAA) without a worldwide referendum is ethically unjustifiable. Until a consensus is reached on whether to bring into existence such technology, a global moratorium is required (*we already have AGI).

I thought it might be useful to spell that out.

I recently discovered the idea of driving all blames into oneself, which immediately resonated with me. It is relatively hardcore; the kind of thing that would turn David Goggins into a Buddhist.

Gemini did a good job of summarising it:

This quote by Pema Chödron, a renowned Buddhist teacher, represents a core principle in some Buddhist traditions, particularly within Tibetan Buddhism. It's called "taking full responsibility" or "taking self-blame" and can be a bit challenging to understand at first. Here's a breakdown:

What it Doesn't Mean:

• Self-Flagellation: This practice isn't about beating yourself up or dwelling on guilt.
• Ignoring External Factors: It doesn't deny the role of external circumstances in a situation.

What it Does Mean:

• Owning Your Reaction: It's about acknowledging how a situation makes you feel and taking responsibility for your own emotional response.
• Shifting Focus: Instead of blaming others or dwelling on what you can't control, you direct your attention to your own thoughts and reactions.
• Breaking Negative Cycles: By understanding your own reactions, you can break free from negative thought patterns and choose a more skillful response.

Analogy:

Imagine a pebble thrown into a still pond. The pebble represents the external situation, and the ripples represent your emotional response. While you can't control the pebble (the external situation), you can control the ripples (your reaction).

Benefits:

• Reduced Suffering: By taking responsibility for your own reactions, you become less dependent on external circumstances for your happiness.
• Increased Self-Awareness: It helps you understand your triggers and cultivate a more mindful response to situations.
• Greater Personal Growth: By taking responsibility, you empower yourself to learn and grow from experiences.

Here are some additional points to consider:

• This practice doesn't mean excusing bad behavior. You can still hold others accountable while taking responsibility for your own reactions.
• It's a gradual process. Be patient with yourself as you learn to practice this approach.

What are some historical examples of a group (like AI Safety folk) getting something incredibly wrong about an incoming Technology? Bonus question: what led to that group getting it so wrong? Maybe there is something to learn here.

I have heard rumours that an AI Safety documentary is being made. Separate to this, a good friend of mine is also seriously considering making one, but he isn't "in" AI Safety. If you know who this first group is and can put me in touch with them, it might be worth getting across each others plans.

One of the seminal texts in marketing science is The Long and The Short of it by Field and Binet. They argue that for maximum effectiveness, marketing should aim to create two distinct work streams and results; immediate sales and longer term sales. 

They argue the tactics that go into either are distinct (e.g. short term = create a sense of urgency, long term = match brand associations with category associations). 

This feels like a good analogy for AI Safety Advocacy / Governance - keep talking about short term things people can buy now (in an Australian context that is the AI Safety Institute) while maintaining salience on the long term (x-risk, a global Pause, etc).

The question shouldn't be either/or, rather, its about how much (%) effort should go into either at any point in time.

What would be the pros and cons of adding a semi-hidden-but-permanent Hot Takes section to the Forum? All of my takes are Hot and due to time constraints I would otherwise not post at all. Some would argue that someone like me should not post Hot Takes at all. Anyway, in true lazy fashion here is ChatGPT on the pros and cons:

Pros:

• Encourages diverse perspectives and stimulates debate.
• Can attract more engagement and interest from users.
• Provides a platform for expressing unconventional or controversial ideas.
• Fosters a culture of intellectual curiosity and open discourse within the community.

Cons:

• May lead to increased polarization and conflict within the community.
• Risk of spreading misinformation or poorly researched opinions.
• Could divert attention from more rigorous and evidence-based discussions.
• Potential for reputational damage if controversial opinions are associated with the forum.

Feels kinda obnoxious to write a quick take along the lines of "I'm thinking about writing a post on X, does anyone actually give a sh*t? Otherwise I won't write it."

I just wanted to check, since I can't place my finger on why it feels obnoxious but it certainly does. 

How impactful could non-dual meditation be for improving wellbeing?

Are there any EAs out there who have practiced non-dual meditation? Specifically, anything from the Dzogchen or Mahamudra traditions of Tibetan Buddhism? 

More secular teachers would be Loch Kelly, Sam Harris, Michael Taft.

This has been a life changing experience for me and I'm wondering whether it could be a blind spot for EA.

I'd also just love to chat with someone else who has experienced non-duality / awakening through this form of meditation :)